Download
Bonsai 27B is a repository for downloading, configuring, and running PrismML’s highly compressed Bonsai language models on local hardware. It supports the 1-bit Bonsai and higher-quality Ternary-Bonsai families in 1.7B, 4B, 8B, and 27B sizes. The models can run on macOS, Linux, and Windows through CPU, Metal, CUDA, Vulkan, ROCm, llama.cpp, or MLX backends. Its 27B models process text, images, screenshots, and PDFs while supporting reasoning and long-context conversations. They also provide OpenAI-compatible tool calling and optional MCP server integration for agentic workflows. Automated setup scripts install dependencies, download models, obtain binaries, and configure interactive interfaces. Users can access the models through command-line prompts, a local chat server, or Open WebUI.
Features
- Local 1-bit and ternary language model inference
- Support for 1.7B, 4B, 8B, and 27B models
- Text, image, screenshot, and PDF understanding
- Adjustable reasoning effort and long-context processing
- OpenAI-style tool calling and MCP integration
- Cross-platform setup for CPU and accelerated hardware
Project Samples
